Unsupervised feature learning for electrocardiogram data using the convolutional variational autoencoder

Most existing electrocardiogram (ECG) feature extraction methods rely on rule-based approaches. It is difficult to manually define all ECG features. We propose an unsupervised feature learning method using a convolutional variational autoencoder (CVAE) that can extract ECG features with unlabeled da...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2021-12, Vol.16 (12), p.e0260612-e0260612
Main Authors: Jang, Jong-Hwan, Kim, Tae Young, Lim, Hong-Seok, Yoon, Dukyong
Format: Article
Language:English
Subjects:
Algorithms
Analysis
Anomalies
Arrhythmia
Arrhythmias, Cardiac - diagnostic imaging
Biology and Life Sciences
Cardiac arrhythmia
Classification
Cluster Analysis
Clustering
Coders
Computer and Information Sciences
Data collection
Databases, Factual
Deep learning
EKG
Electrocardiogram
Electrocardiography
Electrocardiography - methods
Evaluation
Feature extraction
Hospitals
Humans
Image Processing, Computer-Assisted
Informatics
Information management
Intensive care
Intensive care units
Machine learning
Medical tests
Medicine and Health Sciences
Methods
Models, Theoretical
Morphology
Physical Sciences
Research and Analysis Methods
Social Sciences
Space exploration
Transfer learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most existing electrocardiogram (ECG) feature extraction methods rely on rule-based approaches. It is difficult to manually define all ECG features. We propose an unsupervised feature learning method using a convolutional variational autoencoder (CVAE) that can extract ECG features with unlabeled data. We used 596,000 ECG samples from 1,278 patients archived in biosignal databases from intensive care units to train the CVAE. Three external datasets were used for feature validation using two approaches. First, we explored the features without an additional training process. Clustering, latent space exploration, and anomaly detection were conducted. We confirmed that CVAE features reflected the various types of ECG rhythms. Second, we applied CVAE features to new tasks as input data and CVAE weights to weight initialization for different models for transfer learning for the classification of 12 types of arrhythmias. The f1-score for arrhythmia classification with extreme gradient boosting was 0.86 using CVAE features only. The f1-score of the model in which weights were initialized with the CVAE encoder was 5% better than that obtained with random initialization. Unsupervised feature learning with CVAE can extract the characteristics of various types of ECGs and can be an alternative to the feature extraction method for ECGs.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0260612